News
[2024/07] 2 papers (both first author) are accepted by ACM MM 2024!
[2024/03] 1 paper is accepted by TCSVT 2024.
[2024/02] 1 paper is accepted by TIP 2024.
[2023/08] 1 paper is accepted by ACM MM 2023!
[2023/01] 1 paper with Dr. Jiayuan Xie is accepted by TOMM 2023.
|
|
South China University of Technology (SCUT), China
Honours Degree in Software Engineering • Sep. 2019 - Jun. 2023
Excellent Degree Dissertations of SCUT in 2023.
|
|
South China University of Technology (SCUT), China
Key Laboratory of Big Data and Intelligent Robot • Sep. 2023 - Present
Supervisor: Prof. Yi Cai
|
|
Learning to Correction: Explainable Feedback Generation for Visual Commonsense Reasoning Distractor
Jiali Chen, Xusen Hei, Yuqi Xue, Yuancheng Wei, Jiayuan Xie, Yi Cai, Qing Li
ACM Multimedia, ACM MM 2024
[Paperlink], [Code]
Area: Large Multimodal Model, New Benchmark
We present the first work to investigate the error correction capabilities of large multimodal models (LMMs), construct a new benchmark and introduce the feedback generation task for evaluation. I would like to extend my heartfelt gratitude to my girlfriend, Ms. Wen, for inspiring the idea behind this paper.
|
|
Deconfounded Emotion Guidance Sticker Selection with Causal Inference
Jiali Chen, Yi Cai, Ruohang Xu, Jiexin Wang, Jiayuan Xie, Qing Li
ACM Multimedia, ACM MM 2024
[Paperlink]
Area: Bias, Causal Inference, Sticker Selection
This paper presents a Causal Knowledge-Enhanced Sticker Selection model that addresses spurious correlations in sticker selection by using a causal graph and a knowledge-enhanced approach.
|
|
Knowledge-Guided Cross-Topic Visual Question Generation
Hongfei Liu, Guohua Wang, Jiayuan Xie, Jiali Chen, Wenhao Fang, Yi Cai
International Conference on Computational Linguistics, COLING 2024
[Paperlink]
Area: Cross-Topic, Text Generation
We propose a knowledge-guided cross-topic visual question generation (KC-VQG) model to extract unseen topic-related information for question generation.
|
|
Video Question Generation for Dynamic Changes
Jiayuan Xie*, Jiali Chen*, Zhenghao Liu, Qingbao Huang, Yi Cai, Qing Li
IEEE Transactions on Circuits and Systems for Video Technology, TCSVT 2024
[Paperlink], [Code]
Area: Video Understanding, Text Generation
We introduce D-VQG, a difference-aware video question generation model that aims to generate questions about temporal differences in the video.
|
|
Knowledge-Augmented Visual Question Answering with Natural Language Explanation
IEEE Transactions on Image Processing, TIP 2024
[Paperlink], [Code]
Area: VQA, Reasoning, Text Generation
We introduce KICNLE, which generates consistent answer and explanation with external knowledge.
|
|
Diverse Visual Question Generation based on Multiple Objects Selection
Wenhao Fang, Jiayuan Xie, Hongfei Liu, Jiali Chen, Yi Cai
Transactions on Multimedia Computing Communications and Applications, TOMM 2024
[Paperlink]
Area: Diverse Text Generation, Visual Question Generation
We promote the semantic diversity of generated questions beyond the description diversity.
|
|
Deconfounded Visual Question Generation with Causal Inference
Jiali Chen, Zhenjun Guo, Jiayuan Xie, Yi Cai, Qing Li
ACM Multimedia, ACM MM 2023
[Paperlink], [Code]
Area: Bias, Causal Inference, Visual Question Generation
This study first introduces a causal perspective on VQG and adopts the causal graph to analyze spurious correlations among variables. We propose KECVQG mitigates the impact of spurious correlations for VQG.
|
|
Visual Question Generation for Explicit Questioning Purposes based on Target Objects
Jiayuan Xie*, Jiali Chen*, Wenhao Fang, Yi Cai, Qing Li
Neural Network, NN 2023
[Paperlink], [Code]
Area: Controllable Text Generation, Visual Question Generation
We propose a content-controlled question generation model, which generates questions based on a given target object set specified from an image.
|
|
Visual Paraphrase Generation with Key Information Retained
Jiayuan Xie, Jiali Chen, Yi Cai, Qingbao Huang, Qing Li
ACM Transactions on Multimedia Computing, Communications and Applications, TOMM 2023
[Paperlink], [Code]
Area: Vision-Language, Controllable Text Generation
We propose an object-level paraphrase generation model, which generates paraphrases by adjusting the permutation of key objects and modifying their associated descriptions.
|
|
Category-Guided Visual Question Generation
Hongfei Liu, Jiali Chen, Wenhao Fang, Jiayuan Xie, Yi Cai
Proceedings of the AAAI Conference on Artificial Intelligence, AAAI Student Abstract 2023
[Paperlink]
Area: Controllable Text Generation, Visual Question Generation
A category-guided visual question generation model that can generate questions with multiple categories that focus on different objects in an image.
|
Academic Service
Conference Reviewer: ACL, NAACL, EMNLP, ACM MM, KDD, WSDM
Journal Reviewer: IEEE TPAMI, IEEE TIP
|
Honors & Scholarships
First Prize of the 17th National College Student Software Contest, 2024
Excellent Degree Dissertations of SCUT, 2023
Global AI Challenge for Building E&M Facilities Golden Award, 2023
|
Last updated on Jul, 2024
This website template borrowed from [here]
|
|